Skip to Main Content

Informatics Research Labs

Clinical Research Informatics Lab

Cynthia Brandt

cynthia.brandt@yale.edu | 203-737-5762


Lab location: Room 524, Suite 501, 300 George Street

Lab meeting: Monday: 8-12; Tuesday, Wednesday, Friday: 8-4

Rotations available in the spring term.


The Brandt lab focuses on the creative use of informatics tools on clinical and electronic health record data to inform health services research, and on the development and use of informatics systems for clinical and research studies. Areas of research are broad, with current projects focusing on women veteran’s health, and pain and complementary and integrative health.


Translational Informatics

Kei-Hoi Cheung

kei.cheung@yale.edu | 203-737-5783


Lab location: 464 Congress Avenue

Lab meeting: No specific schedule; typically meets with students on Thursdays or Fridays

Rotations preferred in the spring

Professor Cheung’s research interests include the use of new database technologies (e.g., NoSQL), ontologies and data standards (e.g., FAIR data) to enable semantic data integration in the systems biology context. In addition, Professor Cheung is keen on combining semantic technologies with natural language processing (NLP) to facilitate clinical text mining and machine learning. His research has spawned a range of applications across multiple domains including emergency medicine, systems vaccinology, genomics medicine, and Veteran healthcare research. Professor Cheung’s research collaboration spans Yale, VA, and a number of consortia/communities.


Neuroinformatics

Robert McDougal's Lab

robert.mcdougal@yale.edu | 203-737-4828


Lab location: Suite 501, 300 George St.

Rotations available any time.


The McDougal lab seeks to gain insight into brain function in health and disease. We are interested in both methods of development - e.g. for deriving information from the neuroscience literature and for biophysical simulation - and application. Biological interests range from the systems level -- ischemic stroke, Alzheimer's, working memory -- to the subcellular level, e.g. how are ion channels distributed, and predicting the implications of this distribution on cellular and network behavior.

Potential project areas include:
  1. Investigate the effects of ischemic stroke and its aftermath - design models, run simulations, test hypotheses to gain insights on how to maximize neuron survival following a stroke.
  2. Alzheimer’s data mining - help identify promising treatments by applying tools to mine the literature to look for treatments showing promise in a wide range of model organisms.
  3. Neuroscience data sharing - use text mining to identify experimentally derived neuron properties or computational models in the literature along with relevant metadata.
  4. Machine learning of neuronal dynamics - combine machine learning and simulation to build a statistical characterization of a biophysical computational model cell.
  5. Morphology studies - use simulation to investigate how neuron morphology shapes their internal processes.

Information Science

Samah Fodeh Jarad

samah.fodeh@yale.edu | 203-737-5806


Lab location: Room 518, Suite 501, 300 George Street

Lab meeting: Fridays

Rotations available anytime.


The Data Mining lab led by Dr. Fodeh seeks to develop innovative methodologies to address challenging problems in healthcare and biomedical informatics. The current focus of the group is analysis of exceedingly large data sets; especially those that arise in the application areas of text mining, information retrieval and extraction, machine learning and deep learning. The emphasis of the lab is developing and applying sound algorithms that utilize and combine multiple data modalities for central tasks such as prediction and clustering of highdimensional big data. Uncovering the latent low-dimensional structure of big data that preserves sparsity and nonnegativity is essential to enhance representation, interpretation, and by extension success of algorithms. With the above goals in mind, the lab has recently been exploring difficulties associated with phenotyping different types of headaches and associated pharmacological and non-pharmacological therapies, mining social media and healthcare data for suicide and opioid overdose prediction, mining patient-generated data to characterize types of communication between patients and healthcare providers, and exploiting PubMed articles for gene molecular function prediction. The Data Mining lab has released the findings of multiple prior publications addressing those problems. The team meets every Friday and motivated students are always welcome to join the lab.